You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
2459 lines
84 KiB
2459 lines
84 KiB
from datetime import datetime
|
|
from itertools import permutations
|
|
import struct
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from pandas._libs import (
|
|
algos as libalgos,
|
|
hashtable as ht,
|
|
)
|
|
import pandas.util._test_decorators as td
|
|
|
|
from pandas.core.dtypes.common import (
|
|
is_bool_dtype,
|
|
is_complex_dtype,
|
|
is_float_dtype,
|
|
is_integer_dtype,
|
|
is_object_dtype,
|
|
)
|
|
from pandas.core.dtypes.dtypes import CategoricalDtype as CDT
|
|
|
|
import pandas as pd
|
|
from pandas import (
|
|
Categorical,
|
|
CategoricalIndex,
|
|
DataFrame,
|
|
DatetimeIndex,
|
|
Index,
|
|
IntervalIndex,
|
|
MultiIndex,
|
|
NaT,
|
|
Period,
|
|
PeriodIndex,
|
|
Series,
|
|
Timedelta,
|
|
Timestamp,
|
|
date_range,
|
|
timedelta_range,
|
|
to_datetime,
|
|
to_timedelta,
|
|
)
|
|
import pandas._testing as tm
|
|
import pandas.core.algorithms as algos
|
|
from pandas.core.arrays import DatetimeArray
|
|
import pandas.core.common as com
|
|
|
|
|
|
class TestFactorize:
|
|
@pytest.mark.parametrize("sort", [True, False])
|
|
def test_factorize(self, index_or_series_obj, sort):
|
|
obj = index_or_series_obj
|
|
result_codes, result_uniques = obj.factorize(sort=sort)
|
|
|
|
constructor = Index
|
|
if isinstance(obj, MultiIndex):
|
|
constructor = MultiIndex.from_tuples
|
|
expected_uniques = constructor(obj.unique())
|
|
|
|
if sort:
|
|
expected_uniques = expected_uniques.sort_values()
|
|
|
|
# construct an integer ndarray so that
|
|
# `expected_uniques.take(expected_codes)` is equal to `obj`
|
|
expected_uniques_list = list(expected_uniques)
|
|
expected_codes = [expected_uniques_list.index(val) for val in obj]
|
|
expected_codes = np.asarray(expected_codes, dtype=np.intp)
|
|
|
|
tm.assert_numpy_array_equal(result_codes, expected_codes)
|
|
tm.assert_index_equal(result_uniques, expected_uniques, exact=True)
|
|
|
|
def test_series_factorize_na_sentinel_none(self):
|
|
# GH#35667
|
|
values = np.array([1, 2, 1, np.nan])
|
|
ser = Series(values)
|
|
codes, uniques = ser.factorize(na_sentinel=None)
|
|
|
|
expected_codes = np.array([0, 1, 0, 2], dtype=np.intp)
|
|
expected_uniques = Index([1.0, 2.0, np.nan])
|
|
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_index_equal(uniques, expected_uniques)
|
|
|
|
def test_basic(self):
|
|
|
|
codes, uniques = algos.factorize(["a", "b", "b", "a", "a", "c", "c", "c"])
|
|
tm.assert_numpy_array_equal(uniques, np.array(["a", "b", "c"], dtype=object))
|
|
|
|
codes, uniques = algos.factorize(
|
|
["a", "b", "b", "a", "a", "c", "c", "c"], sort=True
|
|
)
|
|
exp = np.array([0, 1, 1, 0, 0, 2, 2, 2], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = np.array(["a", "b", "c"], dtype=object)
|
|
tm.assert_numpy_array_equal(uniques, exp)
|
|
|
|
arr = np.arange(5, dtype=np.intp)[::-1]
|
|
|
|
codes, uniques = algos.factorize(arr)
|
|
exp = np.array([0, 1, 2, 3, 4], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = np.array([4, 3, 2, 1, 0], dtype=arr.dtype)
|
|
tm.assert_numpy_array_equal(uniques, exp)
|
|
|
|
codes, uniques = algos.factorize(arr, sort=True)
|
|
exp = np.array([4, 3, 2, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = np.array([0, 1, 2, 3, 4], dtype=arr.dtype)
|
|
tm.assert_numpy_array_equal(uniques, exp)
|
|
|
|
arr = np.arange(5.0)[::-1]
|
|
|
|
codes, uniques = algos.factorize(arr)
|
|
exp = np.array([0, 1, 2, 3, 4], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = np.array([4.0, 3.0, 2.0, 1.0, 0.0], dtype=arr.dtype)
|
|
tm.assert_numpy_array_equal(uniques, exp)
|
|
|
|
codes, uniques = algos.factorize(arr, sort=True)
|
|
exp = np.array([4, 3, 2, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = np.array([0.0, 1.0, 2.0, 3.0, 4.0], dtype=arr.dtype)
|
|
tm.assert_numpy_array_equal(uniques, exp)
|
|
|
|
def test_mixed(self):
|
|
|
|
# doc example reshaping.rst
|
|
x = Series(["A", "A", np.nan, "B", 3.14, np.inf])
|
|
codes, uniques = algos.factorize(x)
|
|
|
|
exp = np.array([0, 0, -1, 1, 2, 3], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = Index(["A", "B", 3.14, np.inf])
|
|
tm.assert_index_equal(uniques, exp)
|
|
|
|
codes, uniques = algos.factorize(x, sort=True)
|
|
exp = np.array([2, 2, -1, 3, 0, 1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = Index([3.14, np.inf, "A", "B"])
|
|
tm.assert_index_equal(uniques, exp)
|
|
|
|
def test_datelike(self):
|
|
|
|
# M8
|
|
v1 = Timestamp("20130101 09:00:00.00004")
|
|
v2 = Timestamp("20130101")
|
|
x = Series([v1, v1, v1, v2, v2, v1])
|
|
codes, uniques = algos.factorize(x)
|
|
|
|
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = DatetimeIndex([v1, v2])
|
|
tm.assert_index_equal(uniques, exp)
|
|
|
|
codes, uniques = algos.factorize(x, sort=True)
|
|
exp = np.array([1, 1, 1, 0, 0, 1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
exp = DatetimeIndex([v2, v1])
|
|
tm.assert_index_equal(uniques, exp)
|
|
|
|
# period
|
|
v1 = Period("201302", freq="M")
|
|
v2 = Period("201303", freq="M")
|
|
x = Series([v1, v1, v1, v2, v2, v1])
|
|
|
|
# periods are not 'sorted' as they are converted back into an index
|
|
codes, uniques = algos.factorize(x)
|
|
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
tm.assert_index_equal(uniques, PeriodIndex([v1, v2]))
|
|
|
|
codes, uniques = algos.factorize(x, sort=True)
|
|
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
tm.assert_index_equal(uniques, PeriodIndex([v1, v2]))
|
|
|
|
# GH 5986
|
|
v1 = to_timedelta("1 day 1 min")
|
|
v2 = to_timedelta("1 day")
|
|
x = Series([v1, v2, v1, v1, v2, v2, v1])
|
|
codes, uniques = algos.factorize(x)
|
|
exp = np.array([0, 1, 0, 0, 1, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
tm.assert_index_equal(uniques, to_timedelta([v1, v2]))
|
|
|
|
codes, uniques = algos.factorize(x, sort=True)
|
|
exp = np.array([1, 0, 1, 1, 0, 0, 1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, exp)
|
|
tm.assert_index_equal(uniques, to_timedelta([v2, v1]))
|
|
|
|
def test_factorize_nan(self):
|
|
# nan should map to na_sentinel, not reverse_indexer[na_sentinel]
|
|
# rizer.factorize should not raise an exception if na_sentinel indexes
|
|
# outside of reverse_indexer
|
|
key = np.array([1, 2, 1, np.nan], dtype="O")
|
|
rizer = ht.ObjectFactorizer(len(key))
|
|
for na_sentinel in (-1, 20):
|
|
ids = rizer.factorize(key, sort=True, na_sentinel=na_sentinel)
|
|
expected = np.array([0, 1, 0, na_sentinel], dtype="int32")
|
|
assert len(set(key)) == len(set(expected))
|
|
tm.assert_numpy_array_equal(pd.isna(key), expected == na_sentinel)
|
|
|
|
# nan still maps to na_sentinel when sort=False
|
|
key = np.array([0, np.nan, 1], dtype="O")
|
|
na_sentinel = -1
|
|
|
|
# TODO(wesm): unused?
|
|
ids = rizer.factorize(key, sort=False, na_sentinel=na_sentinel) # noqa
|
|
|
|
expected = np.array([2, -1, 0], dtype="int32")
|
|
assert len(set(key)) == len(set(expected))
|
|
tm.assert_numpy_array_equal(pd.isna(key), expected == na_sentinel)
|
|
|
|
@pytest.mark.parametrize(
|
|
"data, expected_codes, expected_uniques",
|
|
[
|
|
(
|
|
[(1, 1), (1, 2), (0, 0), (1, 2), "nonsense"],
|
|
[0, 1, 2, 1, 3],
|
|
[(1, 1), (1, 2), (0, 0), "nonsense"],
|
|
),
|
|
(
|
|
[(1, 1), (1, 2), (0, 0), (1, 2), (1, 2, 3)],
|
|
[0, 1, 2, 1, 3],
|
|
[(1, 1), (1, 2), (0, 0), (1, 2, 3)],
|
|
),
|
|
([(1, 1), (1, 2), (0, 0), (1, 2)], [0, 1, 2, 1], [(1, 1), (1, 2), (0, 0)]),
|
|
],
|
|
)
|
|
def test_factorize_tuple_list(self, data, expected_codes, expected_uniques):
|
|
# GH9454
|
|
codes, uniques = pd.factorize(data)
|
|
|
|
tm.assert_numpy_array_equal(codes, np.array(expected_codes, dtype=np.intp))
|
|
|
|
expected_uniques_array = com.asarray_tuplesafe(expected_uniques, dtype=object)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques_array)
|
|
|
|
def test_complex_sorting(self):
|
|
# gh 12666 - check no segfault
|
|
x17 = np.array([complex(i) for i in range(17)], dtype=object)
|
|
|
|
msg = "'[<>]' not supported between instances of .*"
|
|
with pytest.raises(TypeError, match=msg):
|
|
algos.factorize(x17[::-1], sort=True)
|
|
|
|
def test_numeric_dtype_factorize(self, any_real_numpy_dtype):
|
|
# GH41132
|
|
dtype = any_real_numpy_dtype
|
|
data = np.array([1, 2, 2, 1], dtype=dtype)
|
|
expected_codes = np.array([0, 1, 1, 0], dtype=np.intp)
|
|
expected_uniques = np.array([1, 2], dtype=dtype)
|
|
|
|
codes, uniques = algos.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
def test_float64_factorize(self, writable):
|
|
data = np.array([1.0, 1e8, 1.0, 1e-8, 1e8, 1.0], dtype=np.float64)
|
|
data.setflags(write=writable)
|
|
expected_codes = np.array([0, 1, 0, 2, 1, 0], dtype=np.intp)
|
|
expected_uniques = np.array([1.0, 1e8, 1e-8], dtype=np.float64)
|
|
|
|
codes, uniques = algos.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
def test_uint64_factorize(self, writable):
|
|
data = np.array([2**64 - 1, 1, 2**64 - 1], dtype=np.uint64)
|
|
data.setflags(write=writable)
|
|
expected_codes = np.array([0, 1, 0], dtype=np.intp)
|
|
expected_uniques = np.array([2**64 - 1, 1], dtype=np.uint64)
|
|
|
|
codes, uniques = algos.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
def test_int64_factorize(self, writable):
|
|
data = np.array([2**63 - 1, -(2**63), 2**63 - 1], dtype=np.int64)
|
|
data.setflags(write=writable)
|
|
expected_codes = np.array([0, 1, 0], dtype=np.intp)
|
|
expected_uniques = np.array([2**63 - 1, -(2**63)], dtype=np.int64)
|
|
|
|
codes, uniques = algos.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
def test_string_factorize(self, writable):
|
|
data = np.array(["a", "c", "a", "b", "c"], dtype=object)
|
|
data.setflags(write=writable)
|
|
expected_codes = np.array([0, 1, 0, 2, 1], dtype=np.intp)
|
|
expected_uniques = np.array(["a", "c", "b"], dtype=object)
|
|
|
|
codes, uniques = algos.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
def test_object_factorize(self, writable):
|
|
data = np.array(["a", "c", None, np.nan, "a", "b", NaT, "c"], dtype=object)
|
|
data.setflags(write=writable)
|
|
expected_codes = np.array([0, 1, -1, -1, 0, 2, -1, 1], dtype=np.intp)
|
|
expected_uniques = np.array(["a", "c", "b"], dtype=object)
|
|
|
|
codes, uniques = algos.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
def test_datetime64_factorize(self, writable):
|
|
# GH35650 Verify whether read-only datetime64 array can be factorized
|
|
data = np.array([np.datetime64("2020-01-01T00:00:00.000")])
|
|
data.setflags(write=writable)
|
|
expected_codes = np.array([0], dtype=np.intp)
|
|
expected_uniques = np.array(
|
|
["2020-01-01T00:00:00.000000000"], dtype="datetime64[ns]"
|
|
)
|
|
|
|
codes, uniques = pd.factorize(data)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
@pytest.mark.parametrize("sort", [True, False])
|
|
def test_factorize_rangeindex(self, sort):
|
|
# increasing -> sort doesn't matter
|
|
ri = pd.RangeIndex.from_range(range(10))
|
|
expected = np.arange(10, dtype=np.intp), ri
|
|
|
|
result = algos.factorize(ri, sort=sort)
|
|
tm.assert_numpy_array_equal(result[0], expected[0])
|
|
tm.assert_index_equal(result[1], expected[1], exact=True)
|
|
|
|
result = ri.factorize(sort=sort)
|
|
tm.assert_numpy_array_equal(result[0], expected[0])
|
|
tm.assert_index_equal(result[1], expected[1], exact=True)
|
|
|
|
@pytest.mark.parametrize("sort", [True, False])
|
|
def test_factorize_rangeindex_decreasing(self, sort):
|
|
# decreasing -> sort matters
|
|
ri = pd.RangeIndex.from_range(range(10))
|
|
expected = np.arange(10, dtype=np.intp), ri
|
|
|
|
ri2 = ri[::-1]
|
|
expected = expected[0], ri2
|
|
if sort:
|
|
expected = expected[0][::-1], expected[1][::-1]
|
|
|
|
result = algos.factorize(ri2, sort=sort)
|
|
tm.assert_numpy_array_equal(result[0], expected[0])
|
|
tm.assert_index_equal(result[1], expected[1], exact=True)
|
|
|
|
result = ri2.factorize(sort=sort)
|
|
tm.assert_numpy_array_equal(result[0], expected[0])
|
|
tm.assert_index_equal(result[1], expected[1], exact=True)
|
|
|
|
def test_deprecate_order(self):
|
|
# gh 19727 - check warning is raised for deprecated keyword, order.
|
|
# Test not valid once order keyword is removed.
|
|
data = np.array([2**63, 1, 2**63], dtype=np.uint64)
|
|
with pytest.raises(TypeError, match="got an unexpected keyword"):
|
|
algos.factorize(data, order=True)
|
|
with tm.assert_produces_warning(False):
|
|
algos.factorize(data)
|
|
|
|
@pytest.mark.parametrize(
|
|
"data",
|
|
[
|
|
np.array([0, 1, 0], dtype="u8"),
|
|
np.array([-(2**63), 1, -(2**63)], dtype="i8"),
|
|
np.array(["__nan__", "foo", "__nan__"], dtype="object"),
|
|
],
|
|
)
|
|
def test_parametrized_factorize_na_value_default(self, data):
|
|
# arrays that include the NA default for that type, but isn't used.
|
|
codes, uniques = algos.factorize(data)
|
|
expected_uniques = data[[0, 1]]
|
|
expected_codes = np.array([0, 1, 0], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
@pytest.mark.parametrize(
|
|
"data, na_value",
|
|
[
|
|
(np.array([0, 1, 0, 2], dtype="u8"), 0),
|
|
(np.array([1, 0, 1, 2], dtype="u8"), 1),
|
|
(np.array([-(2**63), 1, -(2**63), 0], dtype="i8"), -(2**63)),
|
|
(np.array([1, -(2**63), 1, 0], dtype="i8"), 1),
|
|
(np.array(["a", "", "a", "b"], dtype=object), "a"),
|
|
(np.array([(), ("a", 1), (), ("a", 2)], dtype=object), ()),
|
|
(np.array([("a", 1), (), ("a", 1), ("a", 2)], dtype=object), ("a", 1)),
|
|
],
|
|
)
|
|
def test_parametrized_factorize_na_value(self, data, na_value):
|
|
codes, uniques = algos.factorize_array(data, na_value=na_value)
|
|
expected_uniques = data[[1, 3]]
|
|
expected_codes = np.array([-1, 0, -1, 1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
|
|
@pytest.mark.parametrize("sort", [True, False])
|
|
@pytest.mark.parametrize("na_sentinel", [-1, -10, 100])
|
|
@pytest.mark.parametrize(
|
|
"data, uniques",
|
|
[
|
|
(
|
|
np.array(["b", "a", None, "b"], dtype=object),
|
|
np.array(["b", "a"], dtype=object),
|
|
),
|
|
(
|
|
pd.array([2, 1, np.nan, 2], dtype="Int64"),
|
|
pd.array([2, 1], dtype="Int64"),
|
|
),
|
|
],
|
|
ids=["numpy_array", "extension_array"],
|
|
)
|
|
def test_factorize_na_sentinel(self, sort, na_sentinel, data, uniques):
|
|
codes, uniques = algos.factorize(data, sort=sort, na_sentinel=na_sentinel)
|
|
if sort:
|
|
expected_codes = np.array([1, 0, na_sentinel, 1], dtype=np.intp)
|
|
expected_uniques = algos.safe_sort(uniques)
|
|
else:
|
|
expected_codes = np.array([0, 1, na_sentinel, 0], dtype=np.intp)
|
|
expected_uniques = uniques
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
if isinstance(data, np.ndarray):
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
else:
|
|
tm.assert_extension_array_equal(uniques, expected_uniques)
|
|
|
|
@pytest.mark.parametrize(
|
|
"data, expected_codes, expected_uniques",
|
|
[
|
|
(
|
|
["a", None, "b", "a"],
|
|
np.array([0, 2, 1, 0], dtype=np.dtype("intp")),
|
|
np.array(["a", "b", np.nan], dtype=object),
|
|
),
|
|
(
|
|
["a", np.nan, "b", "a"],
|
|
np.array([0, 2, 1, 0], dtype=np.dtype("intp")),
|
|
np.array(["a", "b", np.nan], dtype=object),
|
|
),
|
|
],
|
|
)
|
|
def test_object_factorize_na_sentinel_none(
|
|
self, data, expected_codes, expected_uniques
|
|
):
|
|
codes, uniques = algos.factorize(data, na_sentinel=None)
|
|
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
|
|
@pytest.mark.parametrize(
|
|
"data, expected_codes, expected_uniques",
|
|
[
|
|
(
|
|
[1, None, 1, 2],
|
|
np.array([0, 2, 0, 1], dtype=np.dtype("intp")),
|
|
np.array([1, 2, np.nan], dtype="O"),
|
|
),
|
|
(
|
|
[1, np.nan, 1, 2],
|
|
np.array([0, 2, 0, 1], dtype=np.dtype("intp")),
|
|
np.array([1, 2, np.nan], dtype=np.float64),
|
|
),
|
|
],
|
|
)
|
|
def test_int_factorize_na_sentinel_none(
|
|
self, data, expected_codes, expected_uniques
|
|
):
|
|
codes, uniques = algos.factorize(data, na_sentinel=None)
|
|
|
|
tm.assert_numpy_array_equal(uniques, expected_uniques)
|
|
tm.assert_numpy_array_equal(codes, expected_codes)
|
|
|
|
|
|
class TestUnique:
|
|
def test_ints(self):
|
|
arr = np.random.randint(0, 100, size=50)
|
|
|
|
result = algos.unique(arr)
|
|
assert isinstance(result, np.ndarray)
|
|
|
|
def test_objects(self):
|
|
arr = np.random.randint(0, 100, size=50).astype("O")
|
|
|
|
result = algos.unique(arr)
|
|
assert isinstance(result, np.ndarray)
|
|
|
|
def test_object_refcount_bug(self):
|
|
lst = ["A", "B", "C", "D", "E"]
|
|
for i in range(1000):
|
|
len(algos.unique(lst))
|
|
|
|
def test_on_index_object(self):
|
|
|
|
mindex = MultiIndex.from_arrays(
|
|
[np.arange(5).repeat(5), np.tile(np.arange(5), 5)]
|
|
)
|
|
expected = mindex.values
|
|
expected.sort()
|
|
|
|
mindex = mindex.repeat(2)
|
|
|
|
result = pd.unique(mindex)
|
|
result.sort()
|
|
|
|
tm.assert_almost_equal(result, expected)
|
|
|
|
def test_dtype_preservation(self, any_numpy_dtype):
|
|
# GH 15442
|
|
if any_numpy_dtype in (tm.BYTES_DTYPES + tm.STRING_DTYPES):
|
|
data = [1, 2, 2]
|
|
uniques = [1, 2]
|
|
elif is_integer_dtype(any_numpy_dtype):
|
|
data = [1, 2, 2]
|
|
uniques = [1, 2]
|
|
elif is_float_dtype(any_numpy_dtype):
|
|
data = [1, 2, 2]
|
|
uniques = [1.0, 2.0]
|
|
elif is_complex_dtype(any_numpy_dtype):
|
|
data = [complex(1, 0), complex(2, 0), complex(2, 0)]
|
|
uniques = [complex(1, 0), complex(2, 0)]
|
|
elif is_bool_dtype(any_numpy_dtype):
|
|
data = [True, True, False]
|
|
uniques = [True, False]
|
|
elif is_object_dtype(any_numpy_dtype):
|
|
data = ["A", "B", "B"]
|
|
uniques = ["A", "B"]
|
|
else:
|
|
# datetime64[ns]/M8[ns]/timedelta64[ns]/m8[ns] tested elsewhere
|
|
data = [1, 2, 2]
|
|
uniques = [1, 2]
|
|
|
|
result = Series(data, dtype=any_numpy_dtype).unique()
|
|
expected = np.array(uniques, dtype=any_numpy_dtype)
|
|
|
|
if any_numpy_dtype in tm.STRING_DTYPES:
|
|
expected = expected.astype(object)
|
|
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_datetime64_dtype_array_returned(self):
|
|
# GH 9431
|
|
expected = np.array(
|
|
[
|
|
"2015-01-03T00:00:00.000000000",
|
|
"2015-01-01T00:00:00.000000000",
|
|
],
|
|
dtype="M8[ns]",
|
|
)
|
|
|
|
dt_index = to_datetime(
|
|
[
|
|
"2015-01-03T00:00:00.000000000",
|
|
"2015-01-01T00:00:00.000000000",
|
|
"2015-01-01T00:00:00.000000000",
|
|
]
|
|
)
|
|
result = algos.unique(dt_index)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
assert result.dtype == expected.dtype
|
|
|
|
s = Series(dt_index)
|
|
result = algos.unique(s)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
assert result.dtype == expected.dtype
|
|
|
|
arr = s.values
|
|
result = algos.unique(arr)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
assert result.dtype == expected.dtype
|
|
|
|
def test_datetime_non_ns(self):
|
|
a = np.array(["2000", "2000", "2001"], dtype="datetime64[s]")
|
|
result = pd.unique(a)
|
|
expected = np.array(["2000", "2001"], dtype="datetime64[ns]")
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_timedelta_non_ns(self):
|
|
a = np.array(["2000", "2000", "2001"], dtype="timedelta64[s]")
|
|
result = pd.unique(a)
|
|
expected = np.array([2000000000000, 2001000000000], dtype="timedelta64[ns]")
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_timedelta64_dtype_array_returned(self):
|
|
# GH 9431
|
|
expected = np.array([31200, 45678, 10000], dtype="m8[ns]")
|
|
|
|
td_index = to_timedelta([31200, 45678, 31200, 10000, 45678])
|
|
result = algos.unique(td_index)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
assert result.dtype == expected.dtype
|
|
|
|
s = Series(td_index)
|
|
result = algos.unique(s)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
assert result.dtype == expected.dtype
|
|
|
|
arr = s.values
|
|
result = algos.unique(arr)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
assert result.dtype == expected.dtype
|
|
|
|
def test_uint64_overflow(self):
|
|
s = Series([1, 2, 2**63, 2**63], dtype=np.uint64)
|
|
exp = np.array([1, 2, 2**63], dtype=np.uint64)
|
|
tm.assert_numpy_array_equal(algos.unique(s), exp)
|
|
|
|
def test_nan_in_object_array(self):
|
|
duplicated_items = ["a", np.nan, "c", "c"]
|
|
result = pd.unique(duplicated_items)
|
|
expected = np.array(["a", np.nan, "c"], dtype=object)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_categorical(self):
|
|
|
|
# we are expecting to return in the order
|
|
# of appearance
|
|
expected = Categorical(list("bac"))
|
|
|
|
# we are expecting to return in the order
|
|
# of the categories
|
|
expected_o = Categorical(list("bac"), categories=list("abc"), ordered=True)
|
|
|
|
# GH 15939
|
|
c = Categorical(list("baabc"))
|
|
result = c.unique()
|
|
tm.assert_categorical_equal(result, expected)
|
|
|
|
result = algos.unique(c)
|
|
tm.assert_categorical_equal(result, expected)
|
|
|
|
c = Categorical(list("baabc"), ordered=True)
|
|
result = c.unique()
|
|
tm.assert_categorical_equal(result, expected_o)
|
|
|
|
result = algos.unique(c)
|
|
tm.assert_categorical_equal(result, expected_o)
|
|
|
|
# Series of categorical dtype
|
|
s = Series(Categorical(list("baabc")), name="foo")
|
|
result = s.unique()
|
|
tm.assert_categorical_equal(result, expected)
|
|
|
|
result = pd.unique(s)
|
|
tm.assert_categorical_equal(result, expected)
|
|
|
|
# CI -> return CI
|
|
ci = CategoricalIndex(Categorical(list("baabc"), categories=list("abc")))
|
|
expected = CategoricalIndex(expected)
|
|
result = ci.unique()
|
|
tm.assert_index_equal(result, expected)
|
|
|
|
result = pd.unique(ci)
|
|
tm.assert_index_equal(result, expected)
|
|
|
|
def test_datetime64tz_aware(self):
|
|
# GH 15939
|
|
|
|
result = Series(
|
|
Index(
|
|
[
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
]
|
|
)
|
|
).unique()
|
|
expected = DatetimeArray._from_sequence(
|
|
np.array([Timestamp("2016-01-01 00:00:00-0500", tz="US/Eastern")])
|
|
)
|
|
tm.assert_extension_array_equal(result, expected)
|
|
|
|
result = Index(
|
|
[
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
]
|
|
).unique()
|
|
expected = DatetimeIndex(
|
|
["2016-01-01 00:00:00"], dtype="datetime64[ns, US/Eastern]", freq=None
|
|
)
|
|
tm.assert_index_equal(result, expected)
|
|
|
|
result = pd.unique(
|
|
Series(
|
|
Index(
|
|
[
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
]
|
|
)
|
|
)
|
|
)
|
|
expected = DatetimeArray._from_sequence(
|
|
np.array([Timestamp("2016-01-01", tz="US/Eastern")])
|
|
)
|
|
tm.assert_extension_array_equal(result, expected)
|
|
|
|
result = pd.unique(
|
|
Index(
|
|
[
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
]
|
|
)
|
|
)
|
|
expected = DatetimeIndex(
|
|
["2016-01-01 00:00:00"], dtype="datetime64[ns, US/Eastern]", freq=None
|
|
)
|
|
tm.assert_index_equal(result, expected)
|
|
|
|
def test_order_of_appearance(self):
|
|
# 9346
|
|
# light testing of guarantee of order of appearance
|
|
# these also are the doc-examples
|
|
result = pd.unique(Series([2, 1, 3, 3]))
|
|
tm.assert_numpy_array_equal(result, np.array([2, 1, 3], dtype="int64"))
|
|
|
|
result = pd.unique(Series([2] + [1] * 5))
|
|
tm.assert_numpy_array_equal(result, np.array([2, 1], dtype="int64"))
|
|
|
|
result = pd.unique(Series([Timestamp("20160101"), Timestamp("20160101")]))
|
|
expected = np.array(["2016-01-01T00:00:00.000000000"], dtype="datetime64[ns]")
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = pd.unique(
|
|
Index(
|
|
[
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
Timestamp("20160101", tz="US/Eastern"),
|
|
]
|
|
)
|
|
)
|
|
expected = DatetimeIndex(
|
|
["2016-01-01 00:00:00"], dtype="datetime64[ns, US/Eastern]", freq=None
|
|
)
|
|
tm.assert_index_equal(result, expected)
|
|
|
|
result = pd.unique(list("aabc"))
|
|
expected = np.array(["a", "b", "c"], dtype=object)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = pd.unique(Series(Categorical(list("aabc"))))
|
|
expected = Categorical(list("abc"))
|
|
tm.assert_categorical_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize(
|
|
"arg ,expected",
|
|
[
|
|
(("1", "1", "2"), np.array(["1", "2"], dtype=object)),
|
|
(("foo",), np.array(["foo"], dtype=object)),
|
|
],
|
|
)
|
|
def test_tuple_with_strings(self, arg, expected):
|
|
# see GH 17108
|
|
result = pd.unique(arg)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_obj_none_preservation(self):
|
|
# GH 20866
|
|
arr = np.array(["foo", None], dtype=object)
|
|
result = pd.unique(arr)
|
|
expected = np.array(["foo", None], dtype=object)
|
|
|
|
tm.assert_numpy_array_equal(result, expected, strict_nan=True)
|
|
|
|
def test_signed_zero(self):
|
|
# GH 21866
|
|
a = np.array([-0.0, 0.0])
|
|
result = pd.unique(a)
|
|
expected = np.array([-0.0]) # 0.0 and -0.0 are equivalent
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_different_nans(self):
|
|
# GH 21866
|
|
# create different nans from bit-patterns:
|
|
NAN1 = struct.unpack("d", struct.pack("=Q", 0x7FF8000000000000))[0]
|
|
NAN2 = struct.unpack("d", struct.pack("=Q", 0x7FF8000000000001))[0]
|
|
assert NAN1 != NAN1
|
|
assert NAN2 != NAN2
|
|
a = np.array([NAN1, NAN2]) # NAN1 and NAN2 are equivalent
|
|
result = pd.unique(a)
|
|
expected = np.array([np.nan])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize("el_type", [np.float64, object])
|
|
def test_first_nan_kept(self, el_type):
|
|
# GH 22295
|
|
# create different nans from bit-patterns:
|
|
bits_for_nan1 = 0xFFF8000000000001
|
|
bits_for_nan2 = 0x7FF8000000000001
|
|
NAN1 = struct.unpack("d", struct.pack("=Q", bits_for_nan1))[0]
|
|
NAN2 = struct.unpack("d", struct.pack("=Q", bits_for_nan2))[0]
|
|
assert NAN1 != NAN1
|
|
assert NAN2 != NAN2
|
|
a = np.array([NAN1, NAN2], dtype=el_type)
|
|
result = pd.unique(a)
|
|
assert result.size == 1
|
|
# use bit patterns to identify which nan was kept:
|
|
result_nan_bits = struct.unpack("=Q", struct.pack("d", result[0]))[0]
|
|
assert result_nan_bits == bits_for_nan1
|
|
|
|
def test_do_not_mangle_na_values(self, unique_nulls_fixture, unique_nulls_fixture2):
|
|
# GH 22295
|
|
if unique_nulls_fixture is unique_nulls_fixture2:
|
|
return # skip it, values not unique
|
|
a = np.array([unique_nulls_fixture, unique_nulls_fixture2], dtype=object)
|
|
result = pd.unique(a)
|
|
assert result.size == 2
|
|
assert a[0] is unique_nulls_fixture
|
|
assert a[1] is unique_nulls_fixture2
|
|
|
|
|
|
class TestIsin:
|
|
def test_invalid(self):
|
|
|
|
msg = (
|
|
r"only list-like objects are allowed to be passed to isin\(\), "
|
|
r"you passed a \[int\]"
|
|
)
|
|
with pytest.raises(TypeError, match=msg):
|
|
algos.isin(1, 1)
|
|
with pytest.raises(TypeError, match=msg):
|
|
algos.isin(1, [1])
|
|
with pytest.raises(TypeError, match=msg):
|
|
algos.isin([1], 1)
|
|
|
|
def test_basic(self):
|
|
|
|
result = algos.isin([1, 2], [1])
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(np.array([1, 2]), [1])
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(Series([1, 2]), [1])
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(Series([1, 2]), Series([1]))
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(Series([1, 2]), {1})
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(["a", "b"], ["a"])
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(Series(["a", "b"]), Series(["a"]))
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(Series(["a", "b"]), {"a"})
|
|
expected = np.array([True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(["a", "b"], [1])
|
|
expected = np.array([False, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_i8(self):
|
|
|
|
arr = date_range("20130101", periods=3).values
|
|
result = algos.isin(arr, [arr[0]])
|
|
expected = np.array([True, False, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(arr, arr[0:2])
|
|
expected = np.array([True, True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(arr, set(arr[0:2]))
|
|
expected = np.array([True, True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
arr = timedelta_range("1 day", periods=3).values
|
|
result = algos.isin(arr, [arr[0]])
|
|
expected = np.array([True, False, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(arr, arr[0:2])
|
|
expected = np.array([True, True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.isin(arr, set(arr[0:2]))
|
|
expected = np.array([True, True, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize("dtype1", ["m8[ns]", "M8[ns]", "M8[ns, UTC]", "period[D]"])
|
|
@pytest.mark.parametrize("dtype", ["i8", "f8", "u8"])
|
|
def test_isin_datetimelike_values_numeric_comps(self, dtype, dtype1):
|
|
# Anything but object and we get all-False shortcut
|
|
|
|
dta = date_range("2013-01-01", periods=3)._values
|
|
if dtype1 == "period[D]":
|
|
# TODO: fix Series.view to get this on its own
|
|
arr = dta.to_period("D")
|
|
elif dtype1 == "M8[ns, UTC]":
|
|
# TODO: fix Series.view to get this on its own
|
|
arr = dta.tz_localize("UTC")
|
|
else:
|
|
arr = Series(dta.view("i8")).view(dtype1)._values
|
|
|
|
comps = arr.view("i8").astype(dtype)
|
|
|
|
result = algos.isin(comps, arr)
|
|
expected = np.zeros(comps.shape, dtype=bool)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_large(self):
|
|
s = date_range("20000101", periods=2000000, freq="s").values
|
|
result = algos.isin(s, s[0:2])
|
|
expected = np.zeros(len(s), dtype=bool)
|
|
expected[0] = True
|
|
expected[1] = True
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_categorical_from_codes(self):
|
|
# GH 16639
|
|
vals = np.array([0, 1, 2, 0])
|
|
cats = ["a", "b", "c"]
|
|
Sd = Series(Categorical([1]).from_codes(vals, cats))
|
|
St = Series(Categorical([1]).from_codes(np.array([0, 1]), cats))
|
|
expected = np.array([True, True, False, True])
|
|
result = algos.isin(Sd, St)
|
|
tm.assert_numpy_array_equal(expected, result)
|
|
|
|
def test_categorical_isin(self):
|
|
vals = np.array([0, 1, 2, 0])
|
|
cats = ["a", "b", "c"]
|
|
cat = Categorical([1]).from_codes(vals, cats)
|
|
other = Categorical([1]).from_codes(np.array([0, 1]), cats)
|
|
|
|
expected = np.array([True, True, False, True])
|
|
result = algos.isin(cat, other)
|
|
tm.assert_numpy_array_equal(expected, result)
|
|
|
|
def test_same_nan_is_in(self):
|
|
# GH 22160
|
|
# nan is special, because from " a is b" doesn't follow "a == b"
|
|
# at least, isin() should follow python's "np.nan in [nan] == True"
|
|
# casting to -> np.float64 -> another float-object somewhere on
|
|
# the way could lead jepardize this behavior
|
|
comps = [np.nan] # could be casted to float64
|
|
values = [np.nan]
|
|
expected = np.array([True])
|
|
result = algos.isin(comps, values)
|
|
tm.assert_numpy_array_equal(expected, result)
|
|
|
|
def test_same_nan_is_in_large(self):
|
|
# https://github.com/pandas-dev/pandas/issues/22205
|
|
s = np.tile(1.0, 1_000_001)
|
|
s[0] = np.nan
|
|
result = algos.isin(s, [np.nan, 1])
|
|
expected = np.ones(len(s), dtype=bool)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_same_nan_is_in_large_series(self):
|
|
# https://github.com/pandas-dev/pandas/issues/22205
|
|
s = np.tile(1.0, 1_000_001)
|
|
series = Series(s)
|
|
s[0] = np.nan
|
|
result = series.isin([np.nan, 1])
|
|
expected = Series(np.ones(len(s), dtype=bool))
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
def test_same_object_is_in(self):
|
|
# GH 22160
|
|
# there could be special treatment for nans
|
|
# the user however could define a custom class
|
|
# with similar behavior, then we at least should
|
|
# fall back to usual python's behavior: "a in [a] == True"
|
|
class LikeNan:
|
|
def __eq__(self, other) -> bool:
|
|
return False
|
|
|
|
def __hash__(self):
|
|
return 0
|
|
|
|
a, b = LikeNan(), LikeNan()
|
|
# same object -> True
|
|
tm.assert_numpy_array_equal(algos.isin([a], [a]), np.array([True]))
|
|
# different objects -> False
|
|
tm.assert_numpy_array_equal(algos.isin([a], [b]), np.array([False]))
|
|
|
|
def test_different_nans(self):
|
|
# GH 22160
|
|
# all nans are handled as equivalent
|
|
|
|
comps = [float("nan")]
|
|
values = [float("nan")]
|
|
assert comps[0] is not values[0] # different nan-objects
|
|
|
|
# as list of python-objects:
|
|
result = algos.isin(comps, values)
|
|
tm.assert_numpy_array_equal(np.array([True]), result)
|
|
|
|
# as object-array:
|
|
result = algos.isin(
|
|
np.asarray(comps, dtype=object), np.asarray(values, dtype=object)
|
|
)
|
|
tm.assert_numpy_array_equal(np.array([True]), result)
|
|
|
|
# as float64-array:
|
|
result = algos.isin(
|
|
np.asarray(comps, dtype=np.float64), np.asarray(values, dtype=np.float64)
|
|
)
|
|
tm.assert_numpy_array_equal(np.array([True]), result)
|
|
|
|
def test_no_cast(self):
|
|
# GH 22160
|
|
# ensure 42 is not casted to a string
|
|
comps = ["ss", 42]
|
|
values = ["42"]
|
|
expected = np.array([False, False])
|
|
result = algos.isin(comps, values)
|
|
tm.assert_numpy_array_equal(expected, result)
|
|
|
|
@pytest.mark.parametrize("empty", [[], Series(dtype=object), np.array([])])
|
|
def test_empty(self, empty):
|
|
# see gh-16991
|
|
vals = Index(["a", "b"])
|
|
expected = np.array([False, False])
|
|
|
|
result = algos.isin(vals, empty)
|
|
tm.assert_numpy_array_equal(expected, result)
|
|
|
|
def test_different_nan_objects(self):
|
|
# GH 22119
|
|
comps = np.array(["nan", np.nan * 1j, float("nan")], dtype=object)
|
|
vals = np.array([float("nan")], dtype=object)
|
|
expected = np.array([False, False, True])
|
|
result = algos.isin(comps, vals)
|
|
tm.assert_numpy_array_equal(expected, result)
|
|
|
|
def test_different_nans_as_float64(self):
|
|
# GH 21866
|
|
# create different nans from bit-patterns,
|
|
# these nans will land in different buckets in the hash-table
|
|
# if no special care is taken
|
|
NAN1 = struct.unpack("d", struct.pack("=Q", 0x7FF8000000000000))[0]
|
|
NAN2 = struct.unpack("d", struct.pack("=Q", 0x7FF8000000000001))[0]
|
|
assert NAN1 != NAN1
|
|
assert NAN2 != NAN2
|
|
|
|
# check that NAN1 and NAN2 are equivalent:
|
|
arr = np.array([NAN1, NAN2], dtype=np.float64)
|
|
lookup1 = np.array([NAN1], dtype=np.float64)
|
|
result = algos.isin(arr, lookup1)
|
|
expected = np.array([True, True])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
lookup2 = np.array([NAN2], dtype=np.float64)
|
|
result = algos.isin(arr, lookup2)
|
|
expected = np.array([True, True])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
def test_isin_int_df_string_search(self):
|
|
"""Comparing df with int`s (1,2) with a string at isin() ("1")
|
|
-> should not match values because int 1 is not equal str 1"""
|
|
df = DataFrame({"values": [1, 2]})
|
|
result = df.isin(["1"])
|
|
expected_false = DataFrame({"values": [False, False]})
|
|
tm.assert_frame_equal(result, expected_false)
|
|
|
|
def test_isin_nan_df_string_search(self):
|
|
"""Comparing df with nan value (np.nan,2) with a string at isin() ("NaN")
|
|
-> should not match values because np.nan is not equal str NaN"""
|
|
df = DataFrame({"values": [np.nan, 2]})
|
|
result = df.isin(["NaN"])
|
|
expected_false = DataFrame({"values": [False, False]})
|
|
tm.assert_frame_equal(result, expected_false)
|
|
|
|
def test_isin_float_df_string_search(self):
|
|
"""Comparing df with floats (1.4245,2.32441) with a string at isin() ("1.4245")
|
|
-> should not match values because float 1.4245 is not equal str 1.4245"""
|
|
df = DataFrame({"values": [1.4245, 2.32441]})
|
|
result = df.isin(["1.4245"])
|
|
expected_false = DataFrame({"values": [False, False]})
|
|
tm.assert_frame_equal(result, expected_false)
|
|
|
|
|
|
class TestValueCounts:
|
|
def test_value_counts(self):
|
|
np.random.seed(1234)
|
|
from pandas.core.reshape.tile import cut
|
|
|
|
arr = np.random.randn(4)
|
|
factor = cut(arr, 4)
|
|
|
|
# assert isinstance(factor, n)
|
|
result = algos.value_counts(factor)
|
|
breaks = [-1.194, -0.535, 0.121, 0.777, 1.433]
|
|
index = IntervalIndex.from_breaks(breaks).astype(CDT(ordered=True))
|
|
expected = Series([1, 1, 1, 1], index=index)
|
|
tm.assert_series_equal(result.sort_index(), expected.sort_index())
|
|
|
|
def test_value_counts_bins(self):
|
|
s = [1, 2, 3, 4]
|
|
result = algos.value_counts(s, bins=1)
|
|
expected = Series([4], index=IntervalIndex.from_tuples([(0.996, 4.0)]))
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
result = algos.value_counts(s, bins=2, sort=False)
|
|
expected = Series(
|
|
[2, 2], index=IntervalIndex.from_tuples([(0.996, 2.5), (2.5, 4.0)])
|
|
)
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
def test_value_counts_dtypes(self):
|
|
result = algos.value_counts([1, 1.0])
|
|
assert len(result) == 1
|
|
|
|
result = algos.value_counts([1, 1.0], bins=1)
|
|
assert len(result) == 1
|
|
|
|
result = algos.value_counts(Series([1, 1.0, "1"])) # object
|
|
assert len(result) == 2
|
|
|
|
msg = "bins argument only works with numeric data"
|
|
with pytest.raises(TypeError, match=msg):
|
|
algos.value_counts(["1", 1], bins=1)
|
|
|
|
def test_value_counts_nat(self):
|
|
td = Series([np.timedelta64(10000), NaT], dtype="timedelta64[ns]")
|
|
dt = to_datetime(["NaT", "2014-01-01"])
|
|
|
|
for s in [td, dt]:
|
|
vc = algos.value_counts(s)
|
|
vc_with_na = algos.value_counts(s, dropna=False)
|
|
assert len(vc) == 1
|
|
assert len(vc_with_na) == 2
|
|
|
|
exp_dt = Series({Timestamp("2014-01-01 00:00:00"): 1})
|
|
tm.assert_series_equal(algos.value_counts(dt), exp_dt)
|
|
# TODO same for (timedelta)
|
|
|
|
def test_value_counts_datetime_outofbounds(self):
|
|
# GH 13663
|
|
s = Series(
|
|
[
|
|
datetime(3000, 1, 1),
|
|
datetime(5000, 1, 1),
|
|
datetime(5000, 1, 1),
|
|
datetime(6000, 1, 1),
|
|
datetime(3000, 1, 1),
|
|
datetime(3000, 1, 1),
|
|
]
|
|
)
|
|
res = s.value_counts()
|
|
|
|
exp_index = Index(
|
|
[datetime(3000, 1, 1), datetime(5000, 1, 1), datetime(6000, 1, 1)],
|
|
dtype=object,
|
|
)
|
|
exp = Series([3, 2, 1], index=exp_index)
|
|
tm.assert_series_equal(res, exp)
|
|
|
|
# GH 12424
|
|
res = to_datetime(Series(["2362-01-01", np.nan]), errors="ignore")
|
|
exp = Series(["2362-01-01", np.nan], dtype=object)
|
|
tm.assert_series_equal(res, exp)
|
|
|
|
def test_categorical(self):
|
|
s = Series(Categorical(list("aaabbc")))
|
|
result = s.value_counts()
|
|
expected = Series([3, 2, 1], index=CategoricalIndex(["a", "b", "c"]))
|
|
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
|
|
# preserve order?
|
|
s = s.cat.as_ordered()
|
|
result = s.value_counts()
|
|
expected.index = expected.index.as_ordered()
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
|
|
def test_categorical_nans(self):
|
|
s = Series(Categorical(list("aaaaabbbcc"))) # 4,3,2,1 (nan)
|
|
s.iloc[1] = np.nan
|
|
result = s.value_counts()
|
|
expected = Series(
|
|
[4, 3, 2],
|
|
index=CategoricalIndex(["a", "b", "c"], categories=["a", "b", "c"]),
|
|
)
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
result = s.value_counts(dropna=False)
|
|
expected = Series([4, 3, 2, 1], index=CategoricalIndex(["a", "b", "c", np.nan]))
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
|
|
# out of order
|
|
s = Series(
|
|
Categorical(list("aaaaabbbcc"), ordered=True, categories=["b", "a", "c"])
|
|
)
|
|
s.iloc[1] = np.nan
|
|
result = s.value_counts()
|
|
expected = Series(
|
|
[4, 3, 2],
|
|
index=CategoricalIndex(
|
|
["a", "b", "c"], categories=["b", "a", "c"], ordered=True
|
|
),
|
|
)
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
|
|
result = s.value_counts(dropna=False)
|
|
expected = Series(
|
|
[4, 3, 2, 1],
|
|
index=CategoricalIndex(
|
|
["a", "b", "c", np.nan], categories=["b", "a", "c"], ordered=True
|
|
),
|
|
)
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
|
|
def test_categorical_zeroes(self):
|
|
# keep the `d` category with 0
|
|
s = Series(Categorical(list("bbbaac"), categories=list("abcd"), ordered=True))
|
|
result = s.value_counts()
|
|
expected = Series(
|
|
[3, 2, 1, 0],
|
|
index=Categorical(
|
|
["b", "a", "c", "d"], categories=list("abcd"), ordered=True
|
|
),
|
|
)
|
|
tm.assert_series_equal(result, expected, check_index_type=True)
|
|
|
|
def test_dropna(self):
|
|
# https://github.com/pandas-dev/pandas/issues/9443#issuecomment-73719328
|
|
|
|
tm.assert_series_equal(
|
|
Series([True, True, False]).value_counts(dropna=True),
|
|
Series([2, 1], index=[True, False]),
|
|
)
|
|
tm.assert_series_equal(
|
|
Series([True, True, False]).value_counts(dropna=False),
|
|
Series([2, 1], index=[True, False]),
|
|
)
|
|
|
|
tm.assert_series_equal(
|
|
Series([True] * 3 + [False] * 2 + [None] * 5).value_counts(dropna=True),
|
|
Series([3, 2], index=[True, False]),
|
|
)
|
|
tm.assert_series_equal(
|
|
Series([True] * 5 + [False] * 3 + [None] * 2).value_counts(dropna=False),
|
|
Series([5, 3, 2], index=[True, False, np.nan]),
|
|
)
|
|
tm.assert_series_equal(
|
|
Series([10.3, 5.0, 5.0]).value_counts(dropna=True),
|
|
Series([2, 1], index=[5.0, 10.3]),
|
|
)
|
|
tm.assert_series_equal(
|
|
Series([10.3, 5.0, 5.0]).value_counts(dropna=False),
|
|
Series([2, 1], index=[5.0, 10.3]),
|
|
)
|
|
|
|
tm.assert_series_equal(
|
|
Series([10.3, 5.0, 5.0, None]).value_counts(dropna=True),
|
|
Series([2, 1], index=[5.0, 10.3]),
|
|
)
|
|
|
|
result = Series([10.3, 10.3, 5.0, 5.0, 5.0, None]).value_counts(dropna=False)
|
|
expected = Series([3, 2, 1], index=[5.0, 10.3, np.nan])
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize("dtype", (np.float64, object, "M8[ns]"))
|
|
def test_value_counts_normalized(self, dtype):
|
|
# GH12558
|
|
s = Series([1] * 2 + [2] * 3 + [np.nan] * 5)
|
|
s_typed = s.astype(dtype)
|
|
result = s_typed.value_counts(normalize=True, dropna=False)
|
|
expected = Series(
|
|
[0.5, 0.3, 0.2], index=Series([np.nan, 2.0, 1.0], dtype=dtype)
|
|
)
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
result = s_typed.value_counts(normalize=True, dropna=True)
|
|
expected = Series([0.6, 0.4], index=Series([2.0, 1.0], dtype=dtype))
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
def test_value_counts_uint64(self):
|
|
arr = np.array([2**63], dtype=np.uint64)
|
|
expected = Series([1], index=[2**63])
|
|
result = algos.value_counts(arr)
|
|
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
arr = np.array([-1, 2**63], dtype=object)
|
|
expected = Series([1, 1], index=[-1, 2**63])
|
|
result = algos.value_counts(arr)
|
|
|
|
tm.assert_series_equal(result, expected)
|
|
|
|
|
|
class TestDuplicated:
|
|
def test_duplicated_with_nas(self):
|
|
keys = np.array([0, 1, np.nan, 0, 2, np.nan], dtype=object)
|
|
|
|
result = algos.duplicated(keys)
|
|
expected = np.array([False, False, False, True, False, True])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.duplicated(keys, keep="first")
|
|
expected = np.array([False, False, False, True, False, True])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.duplicated(keys, keep="last")
|
|
expected = np.array([True, False, True, False, False, False])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.duplicated(keys, keep=False)
|
|
expected = np.array([True, False, True, True, False, True])
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
keys = np.empty(8, dtype=object)
|
|
for i, t in enumerate(
|
|
zip([0, 0, np.nan, np.nan] * 2, [0, np.nan, 0, np.nan] * 2)
|
|
):
|
|
keys[i] = t
|
|
|
|
result = algos.duplicated(keys)
|
|
falses = [False] * 4
|
|
trues = [True] * 4
|
|
expected = np.array(falses + trues)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.duplicated(keys, keep="last")
|
|
expected = np.array(trues + falses)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.duplicated(keys, keep=False)
|
|
expected = np.array(trues + trues)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize(
|
|
"case",
|
|
[
|
|
np.array([1, 2, 1, 5, 3, 2, 4, 1, 5, 6]),
|
|
np.array([1.1, 2.2, 1.1, np.nan, 3.3, 2.2, 4.4, 1.1, np.nan, 6.6]),
|
|
np.array(
|
|
[
|
|
1 + 1j,
|
|
2 + 2j,
|
|
1 + 1j,
|
|
5 + 5j,
|
|
3 + 3j,
|
|
2 + 2j,
|
|
4 + 4j,
|
|
1 + 1j,
|
|
5 + 5j,
|
|
6 + 6j,
|
|
]
|
|
),
|
|
np.array(["a", "b", "a", "e", "c", "b", "d", "a", "e", "f"], dtype=object),
|
|
np.array(
|
|
[1, 2**63, 1, 3**5, 10, 2**63, 39, 1, 3**5, 7], dtype=np.uint64
|
|
),
|
|
],
|
|
)
|
|
def test_numeric_object_likes(self, case):
|
|
exp_first = np.array(
|
|
[False, False, True, False, False, True, False, True, True, False]
|
|
)
|
|
exp_last = np.array(
|
|
[True, True, True, True, False, False, False, False, False, False]
|
|
)
|
|
exp_false = exp_first | exp_last
|
|
|
|
res_first = algos.duplicated(case, keep="first")
|
|
tm.assert_numpy_array_equal(res_first, exp_first)
|
|
|
|
res_last = algos.duplicated(case, keep="last")
|
|
tm.assert_numpy_array_equal(res_last, exp_last)
|
|
|
|
res_false = algos.duplicated(case, keep=False)
|
|
tm.assert_numpy_array_equal(res_false, exp_false)
|
|
|
|
# index
|
|
for idx in [Index(case), Index(case, dtype="category")]:
|
|
res_first = idx.duplicated(keep="first")
|
|
tm.assert_numpy_array_equal(res_first, exp_first)
|
|
|
|
res_last = idx.duplicated(keep="last")
|
|
tm.assert_numpy_array_equal(res_last, exp_last)
|
|
|
|
res_false = idx.duplicated(keep=False)
|
|
tm.assert_numpy_array_equal(res_false, exp_false)
|
|
|
|
# series
|
|
for s in [Series(case), Series(case, dtype="category")]:
|
|
res_first = s.duplicated(keep="first")
|
|
tm.assert_series_equal(res_first, Series(exp_first))
|
|
|
|
res_last = s.duplicated(keep="last")
|
|
tm.assert_series_equal(res_last, Series(exp_last))
|
|
|
|
res_false = s.duplicated(keep=False)
|
|
tm.assert_series_equal(res_false, Series(exp_false))
|
|
|
|
def test_datetime_likes(self):
|
|
|
|
dt = [
|
|
"2011-01-01",
|
|
"2011-01-02",
|
|
"2011-01-01",
|
|
"NaT",
|
|
"2011-01-03",
|
|
"2011-01-02",
|
|
"2011-01-04",
|
|
"2011-01-01",
|
|
"NaT",
|
|
"2011-01-06",
|
|
]
|
|
td = [
|
|
"1 days",
|
|
"2 days",
|
|
"1 days",
|
|
"NaT",
|
|
"3 days",
|
|
"2 days",
|
|
"4 days",
|
|
"1 days",
|
|
"NaT",
|
|
"6 days",
|
|
]
|
|
|
|
cases = [
|
|
np.array([Timestamp(d) for d in dt]),
|
|
np.array([Timestamp(d, tz="US/Eastern") for d in dt]),
|
|
np.array([Period(d, freq="D") for d in dt]),
|
|
np.array([np.datetime64(d) for d in dt]),
|
|
np.array([Timedelta(d) for d in td]),
|
|
]
|
|
|
|
exp_first = np.array(
|
|
[False, False, True, False, False, True, False, True, True, False]
|
|
)
|
|
exp_last = np.array(
|
|
[True, True, True, True, False, False, False, False, False, False]
|
|
)
|
|
exp_false = exp_first | exp_last
|
|
|
|
for case in cases:
|
|
res_first = algos.duplicated(case, keep="first")
|
|
tm.assert_numpy_array_equal(res_first, exp_first)
|
|
|
|
res_last = algos.duplicated(case, keep="last")
|
|
tm.assert_numpy_array_equal(res_last, exp_last)
|
|
|
|
res_false = algos.duplicated(case, keep=False)
|
|
tm.assert_numpy_array_equal(res_false, exp_false)
|
|
|
|
# index
|
|
for idx in [
|
|
Index(case),
|
|
Index(case, dtype="category"),
|
|
Index(case, dtype=object),
|
|
]:
|
|
res_first = idx.duplicated(keep="first")
|
|
tm.assert_numpy_array_equal(res_first, exp_first)
|
|
|
|
res_last = idx.duplicated(keep="last")
|
|
tm.assert_numpy_array_equal(res_last, exp_last)
|
|
|
|
res_false = idx.duplicated(keep=False)
|
|
tm.assert_numpy_array_equal(res_false, exp_false)
|
|
|
|
# series
|
|
for s in [
|
|
Series(case),
|
|
Series(case, dtype="category"),
|
|
Series(case, dtype=object),
|
|
]:
|
|
res_first = s.duplicated(keep="first")
|
|
tm.assert_series_equal(res_first, Series(exp_first))
|
|
|
|
res_last = s.duplicated(keep="last")
|
|
tm.assert_series_equal(res_last, Series(exp_last))
|
|
|
|
res_false = s.duplicated(keep=False)
|
|
tm.assert_series_equal(res_false, Series(exp_false))
|
|
|
|
@pytest.mark.parametrize("case", [Index([1, 2, 3]), pd.RangeIndex(0, 3)])
|
|
def test_unique_index(self, case):
|
|
assert case.is_unique is True
|
|
tm.assert_numpy_array_equal(case.duplicated(), np.array([False, False, False]))
|
|
|
|
@pytest.mark.parametrize(
|
|
"arr, uniques",
|
|
[
|
|
(
|
|
[(0, 0), (0, 1), (1, 0), (1, 1), (0, 0), (0, 1), (1, 0), (1, 1)],
|
|
[(0, 0), (0, 1), (1, 0), (1, 1)],
|
|
),
|
|
(
|
|
[("b", "c"), ("a", "b"), ("a", "b"), ("b", "c")],
|
|
[("b", "c"), ("a", "b")],
|
|
),
|
|
([("a", 1), ("b", 2), ("a", 3), ("a", 1)], [("a", 1), ("b", 2), ("a", 3)]),
|
|
],
|
|
)
|
|
def test_unique_tuples(self, arr, uniques):
|
|
# https://github.com/pandas-dev/pandas/issues/16519
|
|
expected = np.empty(len(uniques), dtype=object)
|
|
expected[:] = uniques
|
|
|
|
result = pd.unique(arr)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
@pytest.mark.parametrize(
|
|
"array,expected",
|
|
[
|
|
(
|
|
[1 + 1j, 0, 1, 1j, 1 + 2j, 1 + 2j],
|
|
# Should return a complex dtype in the future
|
|
np.array([(1 + 1j), 0j, (1 + 0j), 1j, (1 + 2j)], dtype=object),
|
|
)
|
|
],
|
|
)
|
|
def test_unique_complex_numbers(self, array, expected):
|
|
# GH 17927
|
|
result = pd.unique(array)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
|
|
class TestHashTable:
|
|
def test_string_hashtable_set_item_signature(self):
|
|
# GH#30419 fix typing in StringHashTable.set_item to prevent segfault
|
|
tbl = ht.StringHashTable()
|
|
|
|
tbl.set_item("key", 1)
|
|
assert tbl.get_item("key") == 1
|
|
|
|
with pytest.raises(TypeError, match="'key' has incorrect type"):
|
|
# key arg typed as string, not object
|
|
tbl.set_item(4, 6)
|
|
with pytest.raises(TypeError, match="'val' has incorrect type"):
|
|
tbl.get_item(4)
|
|
|
|
def test_lookup_nan(self, writable):
|
|
xs = np.array([2.718, 3.14, np.nan, -7, 5, 2, 3])
|
|
# GH 21688 ensure we can deal with readonly memory views
|
|
xs.setflags(write=writable)
|
|
m = ht.Float64HashTable()
|
|
m.map_locations(xs)
|
|
tm.assert_numpy_array_equal(m.lookup(xs), np.arange(len(xs), dtype=np.intp))
|
|
|
|
def test_add_signed_zeros(self):
|
|
# GH 21866 inconsistent hash-function for float64
|
|
# default hash-function would lead to different hash-buckets
|
|
# for 0.0 and -0.0 if there are more than 2^30 hash-buckets
|
|
# but this would mean 16GB
|
|
N = 4 # 12 * 10**8 would trigger the error, if you have enough memory
|
|
m = ht.Float64HashTable(N)
|
|
m.set_item(0.0, 0)
|
|
m.set_item(-0.0, 0)
|
|
assert len(m) == 1 # 0.0 and -0.0 are equivalent
|
|
|
|
def test_add_different_nans(self):
|
|
# GH 21866 inconsistent hash-function for float64
|
|
# create different nans from bit-patterns:
|
|
NAN1 = struct.unpack("d", struct.pack("=Q", 0x7FF8000000000000))[0]
|
|
NAN2 = struct.unpack("d", struct.pack("=Q", 0x7FF8000000000001))[0]
|
|
assert NAN1 != NAN1
|
|
assert NAN2 != NAN2
|
|
# default hash function would lead to different hash-buckets
|
|
# for NAN1 and NAN2 even if there are only 4 buckets:
|
|
m = ht.Float64HashTable()
|
|
m.set_item(NAN1, 0)
|
|
m.set_item(NAN2, 0)
|
|
assert len(m) == 1 # NAN1 and NAN2 are equivalent
|
|
|
|
def test_lookup_overflow(self, writable):
|
|
xs = np.array([1, 2, 2**63], dtype=np.uint64)
|
|
# GH 21688 ensure we can deal with readonly memory views
|
|
xs.setflags(write=writable)
|
|
m = ht.UInt64HashTable()
|
|
m.map_locations(xs)
|
|
tm.assert_numpy_array_equal(m.lookup(xs), np.arange(len(xs), dtype=np.intp))
|
|
|
|
def test_get_unique(self):
|
|
s = Series([1, 2, 2**63, 2**63], dtype=np.uint64)
|
|
exp = np.array([1, 2, 2**63], dtype=np.uint64)
|
|
tm.assert_numpy_array_equal(s.unique(), exp)
|
|
|
|
@pytest.mark.parametrize("nvals", [0, 10]) # resizing to 0 is special case
|
|
@pytest.mark.parametrize(
|
|
"htable, uniques, dtype, safely_resizes",
|
|
[
|
|
(ht.PyObjectHashTable, ht.ObjectVector, "object", False),
|
|
(ht.StringHashTable, ht.ObjectVector, "object", True),
|
|
(ht.Float64HashTable, ht.Float64Vector, "float64", False),
|
|
(ht.Int64HashTable, ht.Int64Vector, "int64", False),
|
|
(ht.Int32HashTable, ht.Int32Vector, "int32", False),
|
|
(ht.UInt64HashTable, ht.UInt64Vector, "uint64", False),
|
|
],
|
|
)
|
|
def test_vector_resize(
|
|
self, writable, htable, uniques, dtype, safely_resizes, nvals
|
|
):
|
|
# Test for memory errors after internal vector
|
|
# reallocations (GH 7157)
|
|
vals = np.array(np.random.randn(1000), dtype=dtype)
|
|
|
|
# GH 21688 ensures we can deal with read-only memory views
|
|
vals.setflags(write=writable)
|
|
|
|
# initialise instances; cannot initialise in parametrization,
|
|
# as otherwise external views would be held on the array (which is
|
|
# one of the things this test is checking)
|
|
htable = htable()
|
|
uniques = uniques()
|
|
|
|
# get_labels may append to uniques
|
|
htable.get_labels(vals[:nvals], uniques, 0, -1)
|
|
# to_array() sets an external_view_exists flag on uniques.
|
|
tmp = uniques.to_array()
|
|
oldshape = tmp.shape
|
|
|
|
# subsequent get_labels() calls can no longer append to it
|
|
# (except for StringHashTables + ObjectVector)
|
|
if safely_resizes:
|
|
htable.get_labels(vals, uniques, 0, -1)
|
|
else:
|
|
with pytest.raises(ValueError, match="external reference.*"):
|
|
htable.get_labels(vals, uniques, 0, -1)
|
|
|
|
uniques.to_array() # should not raise here
|
|
assert tmp.shape == oldshape
|
|
|
|
@pytest.mark.parametrize(
|
|
"htable, tm_dtype",
|
|
[
|
|
(ht.PyObjectHashTable, "String"),
|
|
(ht.StringHashTable, "String"),
|
|
(ht.Float64HashTable, "Float"),
|
|
(ht.Int64HashTable, "Int"),
|
|
(ht.UInt64HashTable, "UInt"),
|
|
],
|
|
)
|
|
def test_hashtable_unique(self, htable, tm_dtype, writable):
|
|
# output of maker has guaranteed unique elements
|
|
maker = getattr(tm, "make" + tm_dtype + "Index")
|
|
s = Series(maker(1000))
|
|
if htable == ht.Float64HashTable:
|
|
# add NaN for float column
|
|
s.loc[500] = np.nan
|
|
elif htable == ht.PyObjectHashTable:
|
|
# use different NaN types for object column
|
|
s.loc[500:502] = [np.nan, None, NaT]
|
|
|
|
# create duplicated selection
|
|
s_duplicated = s.sample(frac=3, replace=True).reset_index(drop=True)
|
|
s_duplicated.values.setflags(write=writable)
|
|
|
|
# drop_duplicates has own cython code (hash_table_func_helper.pxi)
|
|
# and is tested separately; keeps first occurrence like ht.unique()
|
|
expected_unique = s_duplicated.drop_duplicates(keep="first").values
|
|
result_unique = htable().unique(s_duplicated.values)
|
|
tm.assert_numpy_array_equal(result_unique, expected_unique)
|
|
|
|
# test return_inverse=True
|
|
# reconstruction can only succeed if the inverse is correct
|
|
result_unique, result_inverse = htable().unique(
|
|
s_duplicated.values, return_inverse=True
|
|
)
|
|
tm.assert_numpy_array_equal(result_unique, expected_unique)
|
|
reconstr = result_unique[result_inverse]
|
|
tm.assert_numpy_array_equal(reconstr, s_duplicated.values)
|
|
|
|
@pytest.mark.parametrize(
|
|
"htable, tm_dtype",
|
|
[
|
|
(ht.PyObjectHashTable, "String"),
|
|
(ht.StringHashTable, "String"),
|
|
(ht.Float64HashTable, "Float"),
|
|
(ht.Int64HashTable, "Int"),
|
|
(ht.UInt64HashTable, "UInt"),
|
|
],
|
|
)
|
|
def test_hashtable_factorize(self, htable, tm_dtype, writable):
|
|
# output of maker has guaranteed unique elements
|
|
maker = getattr(tm, "make" + tm_dtype + "Index")
|
|
s = Series(maker(1000))
|
|
if htable == ht.Float64HashTable:
|
|
# add NaN for float column
|
|
s.loc[500] = np.nan
|
|
elif htable == ht.PyObjectHashTable:
|
|
# use different NaN types for object column
|
|
s.loc[500:502] = [np.nan, None, NaT]
|
|
|
|
# create duplicated selection
|
|
s_duplicated = s.sample(frac=3, replace=True).reset_index(drop=True)
|
|
s_duplicated.values.setflags(write=writable)
|
|
na_mask = s_duplicated.isna().values
|
|
|
|
result_unique, result_inverse = htable().factorize(s_duplicated.values)
|
|
|
|
# drop_duplicates has own cython code (hash_table_func_helper.pxi)
|
|
# and is tested separately; keeps first occurrence like ht.factorize()
|
|
# since factorize removes all NaNs, we do the same here
|
|
expected_unique = s_duplicated.dropna().drop_duplicates().values
|
|
tm.assert_numpy_array_equal(result_unique, expected_unique)
|
|
|
|
# reconstruction can only succeed if the inverse is correct. Since
|
|
# factorize removes the NaNs, those have to be excluded here as well
|
|
result_reconstruct = result_unique[result_inverse[~na_mask]]
|
|
expected_reconstruct = s_duplicated.dropna().values
|
|
tm.assert_numpy_array_equal(result_reconstruct, expected_reconstruct)
|
|
|
|
@pytest.mark.parametrize(
|
|
"hashtable",
|
|
[
|
|
ht.PyObjectHashTable,
|
|
ht.StringHashTable,
|
|
ht.Float64HashTable,
|
|
ht.Int64HashTable,
|
|
ht.Int32HashTable,
|
|
ht.UInt64HashTable,
|
|
],
|
|
)
|
|
def test_hashtable_large_sizehint(self, hashtable):
|
|
# GH#22729 smoketest for not raising when passing a large size_hint
|
|
size_hint = np.iinfo(np.uint32).max + 1
|
|
hashtable(size_hint=size_hint)
|
|
|
|
|
|
def test_unique_label_indices():
|
|
|
|
a = np.random.randint(1, 1 << 10, 1 << 15).astype(np.intp)
|
|
|
|
left = ht.unique_label_indices(a)
|
|
right = np.unique(a, return_index=True)[1]
|
|
|
|
tm.assert_numpy_array_equal(left, right, check_dtype=False)
|
|
|
|
a[np.random.choice(len(a), 10)] = -1
|
|
left = ht.unique_label_indices(a)
|
|
right = np.unique(a, return_index=True)[1][1:]
|
|
tm.assert_numpy_array_equal(left, right, check_dtype=False)
|
|
|
|
|
|
class TestRank:
|
|
@td.skip_if_no_scipy
|
|
@pytest.mark.parametrize(
|
|
"arr",
|
|
[
|
|
[np.nan, np.nan, 5.0, 5.0, 5.0, np.nan, 1, 2, 3, np.nan],
|
|
[4.0, np.nan, 5.0, 5.0, 5.0, np.nan, 1, 2, 4.0, np.nan],
|
|
],
|
|
)
|
|
def test_scipy_compat(self, arr):
|
|
from scipy.stats import rankdata
|
|
|
|
arr = np.array(arr)
|
|
|
|
mask = ~np.isfinite(arr)
|
|
arr = arr.copy()
|
|
result = libalgos.rank_1d(arr)
|
|
arr[mask] = np.inf
|
|
exp = rankdata(arr)
|
|
exp[mask] = np.nan
|
|
tm.assert_almost_equal(result, exp)
|
|
|
|
@pytest.mark.parametrize("dtype", np.typecodes["AllInteger"])
|
|
def test_basic(self, writable, dtype):
|
|
exp = np.array([1, 2], dtype=np.float64)
|
|
|
|
data = np.array([1, 100], dtype=dtype)
|
|
data.setflags(write=writable)
|
|
ser = Series(data)
|
|
result = algos.rank(ser)
|
|
tm.assert_numpy_array_equal(result, exp)
|
|
|
|
@pytest.mark.parametrize("dtype", [np.float64, np.uint64])
|
|
def test_uint64_overflow(self, dtype):
|
|
exp = np.array([1, 2], dtype=np.float64)
|
|
|
|
s = Series([1, 2**63], dtype=dtype)
|
|
tm.assert_numpy_array_equal(algos.rank(s), exp)
|
|
|
|
def test_too_many_ndims(self):
|
|
arr = np.array([[[1, 2, 3], [4, 5, 6], [7, 8, 9]]])
|
|
msg = "Array with ndim > 2 are not supported"
|
|
|
|
with pytest.raises(TypeError, match=msg):
|
|
algos.rank(arr)
|
|
|
|
@pytest.mark.single_cpu
|
|
@pytest.mark.high_memory
|
|
def test_pct_max_many_rows(self):
|
|
# GH 18271
|
|
values = np.arange(2**24 + 1)
|
|
result = algos.rank(values, pct=True).max()
|
|
assert result == 1
|
|
|
|
values = np.arange(2**25 + 2).reshape(2**24 + 1, 2)
|
|
result = algos.rank(values, pct=True).max()
|
|
assert result == 1
|
|
|
|
|
|
def test_pad_backfill_object_segfault():
|
|
|
|
old = np.array([], dtype="O")
|
|
new = np.array([datetime(2010, 12, 31)], dtype="O")
|
|
|
|
result = libalgos.pad["object"](old, new)
|
|
expected = np.array([-1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = libalgos.pad["object"](new, old)
|
|
expected = np.array([], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = libalgos.backfill["object"](old, new)
|
|
expected = np.array([-1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = libalgos.backfill["object"](new, old)
|
|
expected = np.array([], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
|
|
class TestTseriesUtil:
|
|
def test_backfill(self):
|
|
old = Index([1, 5, 10])
|
|
new = Index(list(range(12)))
|
|
|
|
filler = libalgos.backfill["int64_t"](old.values, new.values)
|
|
|
|
expect_filler = np.array([0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 2, -1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(filler, expect_filler)
|
|
|
|
# corner case
|
|
old = Index([1, 4])
|
|
new = Index(list(range(5, 10)))
|
|
filler = libalgos.backfill["int64_t"](old.values, new.values)
|
|
|
|
expect_filler = np.array([-1, -1, -1, -1, -1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(filler, expect_filler)
|
|
|
|
def test_pad(self):
|
|
old = Index([1, 5, 10])
|
|
new = Index(list(range(12)))
|
|
|
|
filler = libalgos.pad["int64_t"](old.values, new.values)
|
|
|
|
expect_filler = np.array([-1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 2, 2], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(filler, expect_filler)
|
|
|
|
# corner case
|
|
old = Index([5, 10])
|
|
new = Index(np.arange(5))
|
|
filler = libalgos.pad["int64_t"](old.values, new.values)
|
|
expect_filler = np.array([-1, -1, -1, -1, -1], dtype=np.intp)
|
|
tm.assert_numpy_array_equal(filler, expect_filler)
|
|
|
|
|
|
def test_is_lexsorted():
|
|
failure = [
|
|
np.array(
|
|
[
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
3,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
2,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
1,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
0,
|
|
],
|
|
dtype="int64",
|
|
),
|
|
np.array(
|
|
[
|
|
30,
|
|
29,
|
|
28,
|
|
27,
|
|
26,
|
|
25,
|
|
24,
|
|
23,
|
|
22,
|
|
21,
|
|
20,
|
|
19,
|
|
18,
|
|
17,
|
|
16,
|
|
15,
|
|
14,
|
|
13,
|
|
12,
|
|
11,
|
|
10,
|
|
9,
|
|
8,
|
|
7,
|
|
6,
|
|
5,
|
|
4,
|
|
3,
|
|
2,
|
|
1,
|
|
0,
|
|
30,
|
|
29,
|
|
28,
|
|
27,
|
|
26,
|
|
25,
|
|
24,
|
|
23,
|
|
22,
|
|
21,
|
|
20,
|
|
19,
|
|
18,
|
|
17,
|
|
16,
|
|
15,
|
|
14,
|
|
13,
|
|
12,
|
|
11,
|
|
10,
|
|
9,
|
|
8,
|
|
7,
|
|
6,
|
|
5,
|
|
4,
|
|
3,
|
|
2,
|
|
1,
|
|
0,
|
|
30,
|
|
29,
|
|
28,
|
|
27,
|
|
26,
|
|
25,
|
|
24,
|
|
23,
|
|
22,
|
|
21,
|
|
20,
|
|
19,
|
|
18,
|
|
17,
|
|
16,
|
|
15,
|
|
14,
|
|
13,
|
|
12,
|
|
11,
|
|
10,
|
|
9,
|
|
8,
|
|
7,
|
|
6,
|
|
5,
|
|
4,
|
|
3,
|
|
2,
|
|
1,
|
|
0,
|
|
30,
|
|
29,
|
|
28,
|
|
27,
|
|
26,
|
|
25,
|
|
24,
|
|
23,
|
|
22,
|
|
21,
|
|
20,
|
|
19,
|
|
18,
|
|
17,
|
|
16,
|
|
15,
|
|
14,
|
|
13,
|
|
12,
|
|
11,
|
|
10,
|
|
9,
|
|
8,
|
|
7,
|
|
6,
|
|
5,
|
|
4,
|
|
3,
|
|
2,
|
|
1,
|
|
0,
|
|
],
|
|
dtype="int64",
|
|
),
|
|
]
|
|
|
|
assert not libalgos.is_lexsorted(failure)
|
|
|
|
|
|
def test_groupsort_indexer():
|
|
a = np.random.randint(0, 1000, 100).astype(np.intp)
|
|
b = np.random.randint(0, 1000, 100).astype(np.intp)
|
|
|
|
result = libalgos.groupsort_indexer(a, 1000)[0]
|
|
|
|
# need to use a stable sort
|
|
# np.argsort returns int, groupsort_indexer
|
|
# always returns intp
|
|
expected = np.argsort(a, kind="mergesort")
|
|
expected = expected.astype(np.intp)
|
|
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
# compare with lexsort
|
|
# np.lexsort returns int, groupsort_indexer
|
|
# always returns intp
|
|
key = a * 1000 + b
|
|
result = libalgos.groupsort_indexer(key, 1000000)[0]
|
|
expected = np.lexsort((b, a))
|
|
expected = expected.astype(np.intp)
|
|
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
|
|
def test_infinity_sort():
|
|
# GH 13445
|
|
# numpy's argsort can be unhappy if something is less than
|
|
# itself. Instead, let's give our infinities a self-consistent
|
|
# ordering, but outside the float extended real line.
|
|
|
|
Inf = libalgos.Infinity()
|
|
NegInf = libalgos.NegInfinity()
|
|
|
|
ref_nums = [NegInf, float("-inf"), -1e100, 0, 1e100, float("inf"), Inf]
|
|
|
|
assert all(Inf >= x for x in ref_nums)
|
|
assert all(Inf > x or x is Inf for x in ref_nums)
|
|
assert Inf >= Inf and Inf == Inf
|
|
assert not Inf < Inf and not Inf > Inf
|
|
assert libalgos.Infinity() == libalgos.Infinity()
|
|
assert not libalgos.Infinity() != libalgos.Infinity()
|
|
|
|
assert all(NegInf <= x for x in ref_nums)
|
|
assert all(NegInf < x or x is NegInf for x in ref_nums)
|
|
assert NegInf <= NegInf and NegInf == NegInf
|
|
assert not NegInf < NegInf and not NegInf > NegInf
|
|
assert libalgos.NegInfinity() == libalgos.NegInfinity()
|
|
assert not libalgos.NegInfinity() != libalgos.NegInfinity()
|
|
|
|
for perm in permutations(ref_nums):
|
|
assert sorted(perm) == ref_nums
|
|
|
|
# smoke tests
|
|
np.array([libalgos.Infinity()] * 32).argsort()
|
|
np.array([libalgos.NegInfinity()] * 32).argsort()
|
|
|
|
|
|
def test_infinity_against_nan():
|
|
Inf = libalgos.Infinity()
|
|
NegInf = libalgos.NegInfinity()
|
|
|
|
assert not Inf > np.nan
|
|
assert not Inf >= np.nan
|
|
assert not Inf < np.nan
|
|
assert not Inf <= np.nan
|
|
assert not Inf == np.nan
|
|
assert Inf != np.nan
|
|
|
|
assert not NegInf > np.nan
|
|
assert not NegInf >= np.nan
|
|
assert not NegInf < np.nan
|
|
assert not NegInf <= np.nan
|
|
assert not NegInf == np.nan
|
|
assert NegInf != np.nan
|
|
|
|
|
|
def test_ensure_platform_int():
|
|
arr = np.arange(100, dtype=np.intp)
|
|
|
|
result = libalgos.ensure_platform_int(arr)
|
|
assert result is arr
|
|
|
|
|
|
def test_int64_add_overflow():
|
|
# see gh-14068
|
|
msg = "Overflow in int64 addition"
|
|
m = np.iinfo(np.int64).max
|
|
n = np.iinfo(np.int64).min
|
|
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(np.array([m, m]), m)
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(np.array([m, m]), np.array([m, m]))
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(np.array([n, n]), n)
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(np.array([n, n]), np.array([n, n]))
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(np.array([m, n]), np.array([n, n]))
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(
|
|
np.array([m, m]), np.array([m, m]), arr_mask=np.array([False, True])
|
|
)
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(
|
|
np.array([m, m]), np.array([m, m]), b_mask=np.array([False, True])
|
|
)
|
|
with pytest.raises(OverflowError, match=msg):
|
|
algos.checked_add_with_arr(
|
|
np.array([m, m]),
|
|
np.array([m, m]),
|
|
arr_mask=np.array([False, True]),
|
|
b_mask=np.array([False, True]),
|
|
)
|
|
with pytest.raises(OverflowError, match=msg):
|
|
with tm.assert_produces_warning(RuntimeWarning):
|
|
algos.checked_add_with_arr(np.array([m, m]), np.array([np.nan, m]))
|
|
|
|
# Check that the nan boolean arrays override whether or not
|
|
# the addition overflows. We don't check the result but just
|
|
# the fact that an OverflowError is not raised.
|
|
algos.checked_add_with_arr(
|
|
np.array([m, m]), np.array([m, m]), arr_mask=np.array([True, True])
|
|
)
|
|
algos.checked_add_with_arr(
|
|
np.array([m, m]), np.array([m, m]), b_mask=np.array([True, True])
|
|
)
|
|
algos.checked_add_with_arr(
|
|
np.array([m, m]),
|
|
np.array([m, m]),
|
|
arr_mask=np.array([True, False]),
|
|
b_mask=np.array([False, True]),
|
|
)
|
|
|
|
|
|
class TestMode:
|
|
def test_no_mode(self):
|
|
exp = Series([], dtype=np.float64, index=Index([], dtype=int))
|
|
tm.assert_numpy_array_equal(algos.mode([]), exp.values)
|
|
|
|
@pytest.mark.parametrize("dt", np.typecodes["AllInteger"] + np.typecodes["Float"])
|
|
def test_mode_single(self, dt):
|
|
# GH 15714
|
|
exp_single = [1]
|
|
data_single = [1]
|
|
|
|
exp_multi = [1]
|
|
data_multi = [1, 1]
|
|
|
|
ser = Series(data_single, dtype=dt)
|
|
exp = Series(exp_single, dtype=dt)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
ser = Series(data_multi, dtype=dt)
|
|
exp = Series(exp_multi, dtype=dt)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_mode_obj_int(self):
|
|
exp = Series([1], dtype=int)
|
|
tm.assert_numpy_array_equal(algos.mode([1]), exp.values)
|
|
|
|
exp = Series(["a", "b", "c"], dtype=object)
|
|
tm.assert_numpy_array_equal(algos.mode(["a", "b", "c"]), exp.values)
|
|
|
|
@pytest.mark.parametrize("dt", np.typecodes["AllInteger"] + np.typecodes["Float"])
|
|
def test_number_mode(self, dt):
|
|
exp_single = [1]
|
|
data_single = [1] * 5 + [2] * 3
|
|
|
|
exp_multi = [1, 3]
|
|
data_multi = [1] * 5 + [2] * 3 + [3] * 5
|
|
|
|
ser = Series(data_single, dtype=dt)
|
|
exp = Series(exp_single, dtype=dt)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
ser = Series(data_multi, dtype=dt)
|
|
exp = Series(exp_multi, dtype=dt)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_strobj_mode(self):
|
|
exp = ["b"]
|
|
data = ["a"] * 2 + ["b"] * 3
|
|
|
|
ser = Series(data, dtype="c")
|
|
exp = Series(exp, dtype="c")
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
@pytest.mark.parametrize("dt", [str, object])
|
|
def test_strobj_multi_char(self, dt):
|
|
exp = ["bar"]
|
|
data = ["foo"] * 2 + ["bar"] * 3
|
|
|
|
ser = Series(data, dtype=dt)
|
|
exp = Series(exp, dtype=dt)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_datelike_mode(self):
|
|
exp = Series(["1900-05-03", "2011-01-03", "2013-01-02"], dtype="M8[ns]")
|
|
ser = Series(["2011-01-03", "2013-01-02", "1900-05-03"], dtype="M8[ns]")
|
|
tm.assert_extension_array_equal(algos.mode(ser.values), exp._values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
exp = Series(["2011-01-03", "2013-01-02"], dtype="M8[ns]")
|
|
ser = Series(
|
|
["2011-01-03", "2013-01-02", "1900-05-03", "2011-01-03", "2013-01-02"],
|
|
dtype="M8[ns]",
|
|
)
|
|
tm.assert_extension_array_equal(algos.mode(ser.values), exp._values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_timedelta_mode(self):
|
|
exp = Series(["-1 days", "0 days", "1 days"], dtype="timedelta64[ns]")
|
|
ser = Series(["1 days", "-1 days", "0 days"], dtype="timedelta64[ns]")
|
|
tm.assert_extension_array_equal(algos.mode(ser.values), exp._values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
exp = Series(["2 min", "1 day"], dtype="timedelta64[ns]")
|
|
ser = Series(
|
|
["1 day", "1 day", "-1 day", "-1 day 2 min", "2 min", "2 min"],
|
|
dtype="timedelta64[ns]",
|
|
)
|
|
tm.assert_extension_array_equal(algos.mode(ser.values), exp._values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_mixed_dtype(self):
|
|
exp = Series(["foo"])
|
|
ser = Series([1, "foo", "foo"])
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_uint64_overflow(self):
|
|
exp = Series([2**63], dtype=np.uint64)
|
|
ser = Series([1, 2**63, 2**63], dtype=np.uint64)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
exp = Series([1, 2**63], dtype=np.uint64)
|
|
ser = Series([1, 2**63], dtype=np.uint64)
|
|
tm.assert_numpy_array_equal(algos.mode(ser.values), exp.values)
|
|
tm.assert_series_equal(ser.mode(), exp)
|
|
|
|
def test_categorical(self):
|
|
c = Categorical([1, 2])
|
|
exp = c
|
|
msg = "Categorical.mode is deprecated"
|
|
with tm.assert_produces_warning(FutureWarning, match=msg):
|
|
res = c.mode()
|
|
tm.assert_categorical_equal(res, exp)
|
|
|
|
c = Categorical([1, "a", "a"])
|
|
exp = Categorical(["a"], categories=[1, "a"])
|
|
with tm.assert_produces_warning(FutureWarning, match=msg):
|
|
res = c.mode()
|
|
tm.assert_categorical_equal(res, exp)
|
|
|
|
c = Categorical([1, 1, 2, 3, 3])
|
|
exp = Categorical([1, 3], categories=[1, 2, 3])
|
|
with tm.assert_produces_warning(FutureWarning, match=msg):
|
|
res = c.mode()
|
|
tm.assert_categorical_equal(res, exp)
|
|
|
|
def test_index(self):
|
|
idx = Index([1, 2, 3])
|
|
exp = Series([1, 2, 3], dtype=np.int64)
|
|
tm.assert_numpy_array_equal(algos.mode(idx), exp.values)
|
|
|
|
idx = Index([1, "a", "a"])
|
|
exp = Series(["a"], dtype=object)
|
|
tm.assert_numpy_array_equal(algos.mode(idx), exp.values)
|
|
|
|
idx = Index([1, 1, 2, 3, 3])
|
|
exp = Series([1, 3], dtype=np.int64)
|
|
tm.assert_numpy_array_equal(algos.mode(idx), exp.values)
|
|
|
|
idx = Index(
|
|
["1 day", "1 day", "-1 day", "-1 day 2 min", "2 min", "2 min"],
|
|
dtype="timedelta64[ns]",
|
|
)
|
|
with pytest.raises(AttributeError, match="TimedeltaIndex"):
|
|
# algos.mode expects Arraylike, does *not* unwrap TimedeltaIndex
|
|
algos.mode(idx)
|
|
|
|
|
|
class TestDiff:
|
|
@pytest.mark.parametrize("dtype", ["M8[ns]", "m8[ns]"])
|
|
def test_diff_datetimelike_nat(self, dtype):
|
|
# NaT - NaT is NaT, not 0
|
|
arr = np.arange(12).astype(np.int64).view(dtype).reshape(3, 4)
|
|
arr[:, 2] = arr.dtype.type("NaT", "ns")
|
|
result = algos.diff(arr, 1, axis=0)
|
|
|
|
expected = np.ones(arr.shape, dtype="timedelta64[ns]") * 4
|
|
expected[:, 2] = np.timedelta64("NaT", "ns")
|
|
expected[0, :] = np.timedelta64("NaT", "ns")
|
|
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
result = algos.diff(arr.T, 1, axis=1)
|
|
tm.assert_numpy_array_equal(result, expected.T)
|
|
|
|
def test_diff_ea_axis(self):
|
|
dta = date_range("2016-01-01", periods=3, tz="US/Pacific")._data
|
|
|
|
msg = "cannot diff DatetimeArray on axis=1"
|
|
with pytest.raises(ValueError, match=msg):
|
|
algos.diff(dta, 1, axis=1)
|
|
|
|
@pytest.mark.parametrize("dtype", ["int8", "int16"])
|
|
def test_diff_low_precision_int(self, dtype):
|
|
arr = np.array([0, 1, 1, 0, 0], dtype=dtype)
|
|
result = algos.diff(arr, 1)
|
|
expected = np.array([np.nan, 1, 0, -1, 0], dtype="float32")
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
|
|
|
|
@pytest.mark.parametrize("op", [np.array, pd.array])
|
|
def test_union_with_duplicates(op):
|
|
# GH#36289
|
|
lvals = op([3, 1, 3, 4])
|
|
rvals = op([2, 3, 1, 1])
|
|
expected = op([3, 3, 1, 1, 4, 2])
|
|
if isinstance(expected, np.ndarray):
|
|
result = algos.union_with_duplicates(lvals, rvals)
|
|
tm.assert_numpy_array_equal(result, expected)
|
|
else:
|
|
result = algos.union_with_duplicates(lvals, rvals)
|
|
tm.assert_extension_array_equal(result, expected)
|
|
|